© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 17099
    Prev
    Next
    INDEX
    Explanations

    names or aliases used by individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals' names and identities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndum
    -0.69
    inar
    -0.66
    Conclusion
    -0.66
    Increase
    -0.66
    lux
    -0.65
     recons
    -0.64
    artifacts
    -0.61
     brink
    -0.61
    ownt
    -0.60
    haps
    -0.60
    POSITIVE LOGITS
     name
    2.22
     surname
    1.97
     names
    1.82
    name
    1.80
     nickname
    1.79
     initials
    1.74
     pseudonym
    1.71
     moniker
    1.69
     Name
    1.66
    Name
    1.66
    Activations Density 0.501%

    No Known Activations